Browsing by Subject "Circuit"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Artificial Neural Network Circuit for Spectral Pattern Recognition(2013-09-04) Rasheed, FarahArtificial Neural Networks (ANNs) are a massively parallel network of a large number of interconnected neurons similar to the structure of biological neurons in the human brain. ANNs find applications in a large number of fields, from pattern classification problems in Computer Science like handwriting recognition to cancer classification problems in Biomedical Engineering. The parallelism inherent in neural networks makes hardware a good choice to implement ANNs compared to software implementations. The ANNs implemented in this thesis have feedforward architecture and are trained using backpropagation learning algorithm. Different neural network models are trained offline using software and the prediction algorithms are implemented using Verilog and compared with the software models. The circuit implementation of feedforward neural networks is found to be much faster than its software counterpart because of the parallel and pipelined structure as well as the presence of a large number of computations that makes the software simulations slower in comparison. The time taken from input to output by the circuit implementing the feedforward prediction algorithm is measured from the waveform diagram, and it is seen that the circuit implementation of the ANNs provides an increase of over 90% in processing speeds obtained via post-synthesis simulation compared to the software implementation. The ANN models developed in this thesis are plant disease classification, soil clay content classification and handwriting recognition for digits. The accuracy of the ANN model is found to be 75% to 97% for the three different problems. The results obtained from the circuit implementation show a < 1% decrease in accuracy compared with the software simulations because of the use of fixed-point representation for the real numbers. Fixed-point representation of numbers is used instead of floating-point representation for faster computational speed and better resource utilization.Item Dynamically controlling the clock frequency based on the variations in the voltage(2010-08) Chhatbar, Jigar Chandrakant; Abraham, Jacob A.; McDermot, MarkA digital logic circuit tends to become slower if the voltage (VDD) level drops below the normal VDD level. Because of this, the required data will not have settled before the arrival of the clock edge. This results in an incorrect sampling of the data leading to a functional failure of the chip. This thesis proposes a clock controller circuit which solves this issue. It consists of a voltage monitoring circuit to track the variations in the VDD level, a frequency multiplier and divider, and a selector logic circuit that outputs a particular frequency depending upon the VDD range in which the chip is operating.Item Nanoscale graphene for RF circuits and systems(2013-08) Parrish, Kristen Nguyen; Akinwande, DejiIncreased challenges in CMOS scaling have motivated the development of alternatives to silicon circuit technologies, including graphene transistor development. In this work, we present a circuit simulator model for graphene FETs, developed to both fit measured data and predict new behaviors, motivating future research. The model is implemented in Agilent ADS, a circuit level simulator that is commonly used for non-standard transistor technologies, for use with parameter variation analyses, as well as easy integration with CMOS design kits. We present conclusions drawn from the model, including analyses on the effects of contact resistance and oxide scaling. We have also derived a quantum-capacitance limited model, used to intuit intrinsic behaviors of graphene transistors, as well as outline upper bounds on performance. Additionally, the ideal frequency doubler has been examined and compared with graphene, and performance limits for graphene frequency multipliers are elucidated. Performance as a demodulator is also discussed. We leverage this advancement in modeling research to advance circuit- and system-level research using graphene transistor technology. We first explore the development of a GHz planar carbon antenna for use on an RF frontend. This research is further developed in work towards the first standalone carbon radio on flexible plastics. A front end receiver, comprised of an integrated carbon antenna, transmission lines, and a graphene transistor for demodulation, are all fabricated onto one plastic substrate, to be interfaced with speakers for a full radio demo. This complete system will motivate further research on graphene-on-plastic systems.